© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3623
    Prev
    Next
    INDEX
    Explanations

    code structure symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     their
    -1.39
     reflexiones
    -1.36
     these
    -1.34
    𖧷
    -1.31
    ৹
    -1.29
    ẤT
    -1.25
    地区的
    -1.24
    piscina
    -1.24
    negro
    -1.23
    𝚓
    -1.23
    POSITIVE LOGITS
     новых
    1.42
    kém
    1.39
     такая
    1.38
     {
    1.34
     ſy
    1.30
     meinem
    1.26
    <>
    1.26
     procéder
    1.22
    autorelease
    1.20
     unangemessene
    1.20
    Activations Density 0.174%

    No Known Activations